Lead AI Power & Performance Engineer
Lead AI Power & Performance Engineer
- Bangalore, Karnataka, India
- Posted Nov 5, 2026
INDUSTRYSoftware & InternetAI & Machine Learning
Responsibilities
- Define and drive the AI performance benchmarking and workload characterization strategy across CPU, GPU, APU, NPU, and heterogeneous platforms.
- Benchmark AI inference workloads using PyTorch, ONNX Runtime, vLLM, llama.cpp, TensorFlow, and related frameworks and runtimes.
- Analyze key performance metrics, including latency, throughput, time to first token, tokens per second, memory utilization, power consumption, and performance per watt.
- Profile workloads and identify bottlenecks across AI frameworks, runtimes, libraries, drivers, operating systems, firmware, memory subsystems, and hardware.
- Lead complex root-cause analysis and recommend optimizations related to quantization, graph execution, kernels, memory usage, workload scheduling, and heterogeneous compute utilization.
- Conduct competitive benchmarking across AMD and competing CPU, GPU, APU, and AI accelerator platforms.
- Collaborate with SoC architects, framework, runtime, compiler, driver, firmware, and system software teams to improve AI workload performance.
- Develop and improve automation for benchmark execution, data collection, regression analysis, and results visualization.
- Translate benchmarking data into actionable technical recommendations that influence software optimization, hardware design, product strategy, and customer engagements.
- Present technical findings and recommendations to engineering teams, customers, executives, and other cross-functional stakeholders.
- Provide technical leadership, mentor engineers, and drive alignment across multiple teams.
Requirements
- Bachelor’s or master’s degree in Computer Engineering, Electrical Engineering, Computer Science, Artificial Intelligence, Machine Learning, or a related technical field
- Experience in a AI & Machine Learning
Nice to have: ROCm, Ryzen AI Software, Vitis AI, MIGraphX, MLPerf Inference, INT8, INT4, FP16, BF16, mixed-precision execution, large language model inference, Docker, virtualization, containerized AI environments, post-silicon bring-up, early silicon testing, competitive benchmarking, customer-facing performance analysis, platform architecture, software roadmaps, product strategy, customer solutions
Skills
AI performance engineeringsystem performance analysisworkload optimizationbenchmarkingpost-silicon performance validationPyTorchONNX RuntimevLLMllama.cppTensorFlowLinux systemsperformance profilingworkload tracingmemory managementworkload schedulingautomationsystem-level debuggingprofiling tools such as Linux perf, AMD uProf, ROCm Profiler, Nsight Systems, VTune, Perfettohardware architecturememory hierarchydata movementpower and thermal behaviorperformance trade-offsAI optimization techniques such as quantization, mixed-precision inference, graph optimization, operator fusion, kernel tuning, memory optimizationPythonBashCC++PyTorchONNX RuntimevLLMllama.cppTensorFlowLinux perfAMD uProfROCm ProfilerNsight SystemsVTunePerfettoPythonBashCC++
Full description
Company details are for members
Sign up for a free job alert to see Advanced Micro Devices, Inc's profile, website and LinkedIn, and the same for every employer on Referso Jobs.